Overview

This course covers how to think about and model data. We introduce the tools of probabilistic graphical models as a means of representing and manipulating data, modeling uncertainty, and discovering new insights from data. We will particularly emphasize latent variable models, examples of which include latent Dirichlet allocation (for topic modeling), factor analysis, and Gaussian processes. The class will also discuss modeling temporal data (e.g., hidden Markov models), hierarchical models, deep generative models, and structured prediction. On completing this course, students should be able to take a new problem or data set, formulate an appropriate model, learn the model from data, and ultimately answer their original question using inference in the model.

General information

Lecture: Tuesdays, 5:10-7:00pm, in Warren Weaver Hall 102
Recitation/Laboratory (required for all students): Wednesdays, 7:10-8:00pm in Warren Weaver Hall 102

Instructor:		David Sontag		dsontag {@ | at} cs.nyu.edu
Lab instructor:		Rachel Hodos		hodos {@ | at} cims.nyu.edu
Graders:		Prasoon Goyal Justin Chiu		pg1338 {@ | at} nyu.edu jchiu {@ | at} cs.nyu.edu

Office hours: Thursdays, 3:30-4:30pm. Location: 715 Broadway (intersection with Washington Place), 12th Floor, room 1204

Grading: [not finalized] problem sets (55%) + midterm exam (20%) + final exam (20%) + participation (5%). Problem Set policy

Book (required): Kevin Murphy, Machine Learning: a Probabilistic Perspective, MIT Press, 2012. I recommend the latest (4th) printing, as the earlier editions had many typos. You can tell which printing you have as follows: check the inside cover, below the "Library of Congress" information. If it says "10 9 8 ... 4" you've got the (correct) fourth print.

Piazza: We will use Piazza to answer questions and post announcements about the course. Please sign up here. Students' use of Piazza, particularly for adequately answering other students' questions, will contribute toward their participation grade.

Online recordings: Most of the lectures and labs' videos will be posted to techtalks.tv. Note, however, that class attendance is required.

ps1 due Sept. 22 at 3pm
[Solutions]

Reference materials

• Optional course text: Probabilistic Graphical Models: Principles and Techniques by Daphne Koller and Nir Friedman, MIT Press (2009).
• Probabilistic Programming and Bayesian Methods for Hackers by Cam Davidson Pilon
  
• Machine learning books
• Trevor Hastie, Rob Tibshirani, and Jerry Friedman, Elements of Statistical Learning, Second Edition, Springer, 2009. (Can be downloaded as PDF file.)6
• David Barber, Bayesian Reasoning and Machine Learning, Cambridge University Press, 2012. (Can be downloaded as PDF file.)
• Probability
• Chapter 2 of Murphy
  
• Review notes from Stanford's machine learning class
• Sam Roweis's probability review
• Optimization
• Convex Optimization by Stephen Boyd and Lieven Vandenberghe. (Can be downloaded as PDF file.)
  

1. You may discuss a problem with any student in this class, and work together on solving it. This can involve brainstorming and verbally discussing the problem, going together through possible solutions, but should not involve one student telling another a complete solution.

2. Once you solve the homework, you must write up your solutions on your own, without looking at other people's write-ups or giving your write-up to others.

3. In your solution for each problem, you must write down the names of any person with whom you discussed it. This will not affect your grade.

4. Do not consult solution manuals or other people's solutions from similar courses.